Guest Editor(s)
Assoc. Prof. Danilo Avola
Email: avola@di.uniroma1.it
Affiliation: Department of Computer Science, Sapienza University, Rome, Italy
Homepage:
Research Interests: computer vision, explainable AI, Wi-Fi sensing, EEG analysis, biometrics, pattern recognition, multimodal interaction, robotics (UAV & humanoids), human behavior understanding, cognitive & skill transfer models, machine learning & deep learning, medical image and signal analysis, LieToMe systems (deception detection), edge AI & intelligent autonomous systems
Mr. Amedeo Ranaldi
Email: ranaldi@di.uniroma1.it
Affiliation: Department of Computer Science, Sapienza University, Roma, Italy
Homepage:
Research Interests: computer vision, explainable AI, Wi-Fi sensing, intelligent systems, pattern recognition, EEG signal analysis, multimodal learning, multimodal perception, image and video processing, human behavior understanding, machine learning & deep learning
Summary
Recent advances in artificial intelligence have significantly accelerated the development of both unimodal and multimodal perception, as well as computer vision techniques, enabling intelligent systems to interpret and understand complex environments. By leveraging data from images, videos, text, audio, and emerging sensing modalities (e.g., RF and wireless signals), modern AI systems are increasingly capable of supporting decision-making processes across a wide range of real-world scenarios.
These technologies are at the core of numerous applications, including human behavior understanding, intelligent surveillance, robotics, smart cities, healthcare, autonomous systems, and remote sensing. In parallel, the integration of perception with learning-based models has opened new research directions in areas such as action recognition and anticipation, scene understanding, and human-centric analysis.
Despite this progress, several fundamental challenges remain. These include effective representation learning across modalities, robust fusion and alignment strategies, scalability under limited supervision, and the ability to generalize across diverse and dynamic environments. Furthermore, as intelligent systems are increasingly deployed in real-world and safety-critical contexts, issues such as robustness, explainability, and trustworthiness become essential.
This Special Issue aims to bring together cutting-edge research on perception and computer vision for intelligent systems, with a particular emphasis on both multimodal and unimodal approaches. The scope is intentionally broad to encourage interdisciplinary contributions spanning machine learning, signal processing, and real-world system design, fostering innovative solutions that bridge the gap between perception and practical deployment.
Topics of interest include, but are not limited to:
· Multimodal fusion, alignment, and cross-modal learning
· Unimodal and multimodal perception for intelligent systems
· Multi-view, multi-sensor, and distributed perception systems
· Vision-language models, foundation models, and LLM/VLM-assisted perception
· Action recognition, action anticipation, behavior analysis, and human activity understanding
· Object detection, tracking, segmentation, and scene understanding
· Anomaly detection, change detection, and event understanding
· Image and video analysis, restoration, and enhancement
· Self-supervised, weakly supervised, and data-efficient learning
· Domain adaptation, domain generalization, and continual learning
· Robustness, uncertainty estimation, explainability, and trustworthy AI
· Human-centric perception, affective computing, and biometric systems
· Wireless/RF-based sensing and non-visual perception
· Robotics, embodied AI, and autonomous systems
· UAV, aerial, and remote sensing applications
· Smart surveillance, security, and safety-critical systems
· Medical imaging, healthcare applications, and bio-signal analysis
· Edge AI, real-time systems, and efficient model deployment
· Benchmark datasets, evaluation protocols, and real-world applications
Keywords
multimodal perception, computer vision, multimodal fusion and alignment, vision-language models, foundation models, self-supervised learning, robustness and generalization, explainable and trustworthy ai, human-centric perception, agentic AI, physical AI, embodied AI, multimodal reasoning, edge AI
Login
Register
Submit a Paper
Propose a Special lssue